File size: 5,651 Bytes
35702e9 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 | """
Attribution: https://github.com/AIPI540/AIPI540-Deep-Learning-Applications/
Jon Reifschneider
Brinnae Bent
"""
import streamlit as st
from PIL import Image
import numpy as np
import os
import numpy as np
import pandas as pd
import pandas as pd
import json
import matplotlib.pyplot as plt
import os
import urllib.request
import zipfile
import json
import pandas as pd
import time
import torch
import numpy as np
import pandas as pd
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
from torch.utils.data import DataLoader, TensorDataset
from sklearn.model_selection import train_test_split
import matplotlib.pyplot as plt
from sklearn.preprocessing import LabelEncoder
class NNColabFiltering(nn.Module):
def __init__(self, n_playlists, n_artists, embedding_dim_users, embedding_dim_items, n_activations, rating_range):
super().__init__()
self.user_embeddings = nn.Embedding(num_embeddings=n_playlists,embedding_dim=embedding_dim_users)
self.item_embeddings = nn.Embedding(num_embeddings=n_artists,embedding_dim=embedding_dim_items)
self.fc1 = nn.Linear(embedding_dim_users+embedding_dim_items,n_activations)
self.fc2 = nn.Linear(n_activations,1)
self.rating_range = rating_range
def forward(self, X):
# Get embeddings for minibatch
embedded_users = self.user_embeddings(X[:,0])
embedded_items = self.item_embeddings(X[:,1])
# Concatenate user and item embeddings
embeddings = torch.cat([embedded_users,embedded_items],dim=1)
# Pass embeddings through network
preds = self.fc1(embeddings)
preds = F.relu(preds)
preds = self.fc2(preds)
# Scale predicted ratings to target-range [low,high]
preds = torch.sigmoid(preds) * (self.rating_range[1]-self.rating_range[0]) + self.rating_range[0]
return preds
def generate_recommendations(artist_album, playlists, model, playlist_id, device, top_n=10, batch_size=1024):
model.eval()
all_movie_ids = torch.tensor(artist_album['artist_album_id'].values, dtype=torch.long, device=device)
user_ids = torch.full((len(all_movie_ids),), playlist_id, dtype=torch.long, device=device)
# Initialize tensor to store all predictions
all_predictions = torch.zeros(len(all_movie_ids), device=device)
# Generate predictions in batches
with torch.no_grad():
for i in range(0, len(all_movie_ids), batch_size):
batch_user_ids = user_ids[i:i+batch_size]
batch_movie_ids = all_movie_ids[i:i+batch_size]
input_tensor = torch.stack([batch_user_ids, batch_movie_ids], dim=1)
batch_predictions = model(input_tensor).squeeze()
all_predictions[i:i+batch_size] = batch_predictions
# Convert to numpy for easier handling
predictions = all_predictions.cpu().numpy()
albums_listened = set(playlists.loc[playlists['playlist_id'] == playlist_id, 'artist_album_id'].tolist())
unlistened_mask = np.isin(artist_album['artist_album_id'].values, list(albums_listened), invert=True)
# Get top N recommendations
top_indices = np.argsort(predictions[unlistened_mask])[-top_n:][::-1]
recs = artist_album['artist_album_id'].values[unlistened_mask][top_indices]
recs_names = artist_album.loc[artist_album['artist_album_id'].isin(recs)]
album, artist = recs_names['album_name'].values, recs_names['artist_name'].values
return album.tolist(), artist.tolist()
def load_data():
'''
Loads the prefetched data from the output dir
Inputs:
Returns:
artist_album: pandas DataFrame with the best sentiment score
playlists: pandas DataFrame with the worst sentiment score
'''
artist_album = pd.read_csv(os.path.join(os.getcwd() + '/data/processed','artist_album.csv'))
artist_album = artist_album[['artist_album_id','artist_album','artist_name','album_name']].drop_duplicates()
playlists = pd.read_csv(os.path.join(os.getcwd() + '/data/processed','playlists.csv'))
return artist_album, playlists
artist_album, playlists = load_data()
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model = torch.load('models/recommender.pt', map_location=device)
if __name__ == '__main__':
st.header('Spotify Playlists')
img1, img2 = st.columns(2)
music_notes = Image.open('assets/music_notes.png')
img1.image(music_notes, use_column_width=True)
trumpet = Image.open('assets/trumpet.png')
img2.image(trumpet, use_column_width=True)
# Using "with" notation
with st.sidebar:
playlist_name = st.selectbox(
"Playlist Selection",
( list(set(playlists['name'].dropna())) )
)
playlist_id = playlists['playlist_id'][playlists['name'] == playlist_name].values[0]
albums, artists = generate_recommendations(artist_album, playlists, model, playlist_id, device)
st.dataframe(data=playlists[['artist_name','album_name','track_name']][playlists['playlist_id'] == playlist_id])
st.write(f"*Recommendations for playlist:* {playlists['name'][playlists['playlist_id'] == playlist_id].values[0]}")
col1, col2 = st.columns(2)
with col1:
st.write(f'Artist')
with col2:
st.write(f'Album')
for album, artist in zip(albums, artists):
with col1:
st.write(f"**{artist}**")
with col2:
st.write(f"**{album}**")
|